whatmodel.sh / decision / H2O Lightning 31B v1.1

H2O Lightning 31B v1.1

+ contribute

H2O Lightning 31B v1.1 is an open-weights decision model from H2O.ai. Its published size is 31.27B parameters. Licence: other.

Catalogue identity notes

Exact Decision Index tested engine h2o-lightning-31b-v1.1; reported model H2O Lightning 31B v1.1. Type: full fine-tune; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

· Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

70.4±1.5#13 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of H2O Lightning 31B v1.1, out of 357 with a score, then more from H2O.ai.

#	model	score	where	released
11	WeMM-JEV-27B Rover00	71±1	model files
12	KnowLine 35B-A3B Gen1.5 PelaAI	71±2	model files	2026-10-22
13	H2O Lightning 31B v1.1 H2O.ai	70±2	request access
14	Nace.AI Drex Max v1 (27B) Nace-Deepinfra	70±1	model files
15	Bespoke Nimble v4 Max (27B) Bespoke Labs	70±1	model files	2026-10
	more from H2O.ai
38	H2O Lightning 31B H2O.ai	67±4	request access

see all decision models · find the ones that fit your machine

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #32 of 250 · 5.2% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: API-Bank (accuracy) submitted	84.5% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 146/236	easy · avg 70%	▇ 1.5%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	69.2% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 222/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	88.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 199/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	100.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 225/243	medium · avg 37%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.7% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 212/246	very easy · avg 92%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.6% ✎	no other model yet		—	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

retrieval & classification▁▁▁·▁▁▁▁▃▃█▅ #55 of 258 · 8.2% of its score · 7 tests

Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	42.8% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 125/246	medium · avg 38%	▇ 3.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	58.4% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 193/246	medium · avg 47%	▇ 3.0%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	81.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 162/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	82.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 181/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	91.4% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 205/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	95.2% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 207/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	3.4% ✎	no other model yet		—	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

language understanding▂▂▂▃▂▅▆▃█▆▄▃ #42 of 256 · 21% of its score · 9 tests

Beats Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails Decider 35B-A3B, Sieve 9B v2, Clef-flash here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	77.8% ✎	▁▂▃▅▅█▂····▁ beats 223/246	medium · avg 60%	▇▇ 5.5%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	85.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 220/246	easy · avg 74%	▇▇ 5.1%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	65.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 207/246	medium · avg 44%	▇ 2.9%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	95.8% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 205/246	very easy · avg 85%	▇ 2.4%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	46.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 216/246	hard · avg 22%	▇ 2.1%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	80.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 231/246	medium · avg 62%	▇ 1.1%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	83.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 196/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	78.4% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 163/246	easy · avg 66%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	91.7% ✎	▁···▁▁▁▁▃▆█▃ beats 172/246	easy · avg 84%	▇ 0.5%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▃▁ #10 of 247 · 11% of its score · 6 tests

Beats Jeffan-31b-1710, KnowLine 31B Gen1, StartLux-Decision v1.1 27B here, though they rank higher overall. Trails AnyJev Tacitus 31B, baselabs elephant-1 (9B), vera-large here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	84.3% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 240/246	medium · avg 61%	▇▇ 4.0%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	68.7% ✎	▁·▁▃▂▂▅█▄▃▁▁ beats 236/246	medium · avg 60%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.8% ✎	▁········▁▇█ beats 200/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	65.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 189/237	hard · avg 21%	▇ 1.4%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	98.4% ✎	▁█▄▄▅█▆▅▄▃▁▁ beats 237/246	easy · avg 83%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	63.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 234/246	medium · avg 47%	▇ 0.5%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▃ #13 of 263 · 42% of its score · 14 tests

Beats Ainvest-Decision-27B v1.0, StartLux-Decision v1.1 27B, vLLM-SR d3-turbo v1.1 (27B) here, though they rank higher overall. Trails d1 (hosted), Jev 1.13, Matilda Decision v1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	73.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 232/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	87.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 223/246	easy · avg 66%	▇▇ 5.6%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	88.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 232/246	easy · avg 70%	▇▇ 5.4%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	56.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 236/246	medium · avg 39%	▇▇ 4.5%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	88.3% ✎	▁··▄█▆▆▆▅▅▃▁ beats 241/246	medium · avg 45%	▇ 3.6%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	93.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 222/246	easy · avg 78%	▇ 2.6%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	30.1% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 147/246	hard · avg 22%	▇ 2.4%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	69.0% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 208/246	medium · avg 60%	▇ 1.5%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.7% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 230/246	very easy · avg 90%	▇ 1.4%	sharp · maxed out
Decision Index 0.4.1: CRUXEval (accuracy) submitted	86.5% ✎	██▄▃▃▄▁▁···▁ beats 224/246	medium · avg 58%	▇ 1.2%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	24.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 220/246	hard · avg 16%	▇ 1.2%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	89.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 217/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 229/246	very easy · avg 96%	▇ 0.5%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	13.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 157/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 12% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	65.3000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 241/247	avg 41.206 points	▇▇▇ 7.5%	blunt
Decision Index 0.4.1: private new domains (equated points)	73.6400 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 231/247	avg 38.861 points	▇▇ 4.2%	blunt

$ where to run it

Request access to model files ↗
Gated files: the publisher requires access approval. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/h2oai ↗

$ how the score was worked out · Decision Index 0.4.1 99%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Decision Index 0.4.1 · submitted; independent execution unverified	42	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 70.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.6%	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json
Decision Index 0.4.1	Decision Index 0.4.1: SGD/SGD-X (macro-F1) [correct]	3.4%	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-11-03 02:37 UTC · sources and licences · json